# Description There are times where explicitly specifying a schema for a dataframe is needed such as: - Opening CSV and JSON lines files and needing provide more information to polars to keep it from failing or in a desire to override default type conversion - When converting a nushell value to a dataframe and wanting to override the default conversion behaviors. This pull requests provides: - A flag to allow specifying a schema when using dfr into-df - A flag to allow specifying a schema when using dfr open that works for CSV and JSON types - A new command `dfr schema` which displays schema information and will allow display support schema dtypes Schema is specified creating a record that has the key value and the dtype. Examples usages: ``` {a:1, b:{a:2}} | dfr into-df -s {a: u8, b: {a: i32}} | dfr schema {a: 1, b: {a: [1 2 3]}, c: [a b c]} | dfr into-df -s {a: u8, b: {a: list<u64>}, c: list<str>} | dfr schema dfr open -s {pid: i32, ppid: i32, name: str, status: str, cpu: f64, mem: i64, virtual: i64} /tmp/ps.jsonl | dfr schema ``` Supported dtypes: null bool u8 u16 u32 u64 i8 i16 i32 i64 f32 f64 str binary date datetime[time_unit: (ms, us, ns) timezone (optional)] duration[time_unit: (ms, us, ns)] time object unknown list[dtype] structs are also supported but are specified via another record: {a: u8, b: {d: str}} Another feature with the dfr schema command is that it returns the data back in a format that can be passed to provide a valid schema that can be passed in as schema argument: <img width="638" alt="Screenshot 2024-01-29 at 10 23 58" src="https://github.com/nushell/nushell/assets/56345/b49c3bff-5cda-4c86-975a-dfd91d991373"> --------- Co-authored-by: Jack Wright <jack.wright@disqo.com>
83 lines
2.5 KiB
Rust
83 lines
2.5 KiB
Rust
use crate::dataframe::values::{Column, NuDataFrame, NuExpression};
|
|
use nu_engine::CallExt;
|
|
use nu_protocol::{
|
|
ast::Call,
|
|
engine::{Command, EngineState, Stack},
|
|
Category, Example, PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
|
|
};
|
|
use polars::prelude::arg_where;
|
|
|
|
#[derive(Clone)]
|
|
pub struct ExprArgWhere;
|
|
|
|
impl Command for ExprArgWhere {
|
|
fn name(&self) -> &str {
|
|
"dfr arg-where"
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Creates an expression that returns the arguments where expression is true."
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build(self.name())
|
|
.required("column name", SyntaxShape::Any, "Expression to evaluate")
|
|
.input_output_type(Type::Any, Type::Custom("expression".into()))
|
|
.category(Category::Custom("expression".into()))
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![Example {
|
|
description: "Return a dataframe where the value match the expression",
|
|
example: "let df = ([[a b]; [one 1] [two 2] [three 3]] | dfr into-df);
|
|
$df | dfr select (dfr arg-where ((dfr col b) >= 2) | dfr as b_arg)",
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![Column::new(
|
|
"b_arg".to_string(),
|
|
vec![Value::test_int(1), Value::test_int(2)],
|
|
)],
|
|
None,
|
|
)
|
|
.expect("simple df for test should not fail")
|
|
.into_value(Span::test_data()),
|
|
),
|
|
}]
|
|
}
|
|
|
|
fn search_terms(&self) -> Vec<&str> {
|
|
vec!["condition", "match", "if"]
|
|
}
|
|
|
|
fn run(
|
|
&self,
|
|
engine_state: &EngineState,
|
|
stack: &mut Stack,
|
|
call: &Call,
|
|
_input: PipelineData,
|
|
) -> Result<PipelineData, ShellError> {
|
|
let value: Value = call.req(engine_state, stack, 0)?;
|
|
let expr = NuExpression::try_from_value(value)?;
|
|
let expr: NuExpression = arg_where(expr.into_polars()).into();
|
|
|
|
Ok(PipelineData::Value(expr.into_value(call.head), None))
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod test {
|
|
use super::super::super::test_dataframe::test_dataframe;
|
|
use super::*;
|
|
use crate::dataframe::expressions::ExprAlias;
|
|
use crate::dataframe::lazy::LazySelect;
|
|
|
|
#[test]
|
|
fn test_examples() {
|
|
test_dataframe(vec![
|
|
Box::new(ExprArgWhere {}),
|
|
Box::new(ExprAlias {}),
|
|
Box::new(LazySelect {}),
|
|
])
|
|
}
|
|
}
|